DEV Community

Deep Learning

This tag is for discussing, sharing articles, and asking questions primarily on deep learning - a subfield of machine learning.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
JEPA, Explained: What It Actually Does Differently

JEPA, Explained: What It Actually Does Differently

1
Comments
9 min read
Tech & AI Synthesis: Experience-Handoff Reinforcement Learning for Recursive Self-Improvement

Tech & AI Synthesis: Experience-Handoff Reinforcement Learning for Recursive Self-Improvement

Comments
3 min read
DPO vs RLHF: which should you use to align a model?

DPO vs RLHF: which should you use to align a model?

1
Comments
9 min read
How does knowledge distillation work for LLMs?

How does knowledge distillation work for LLMs?

1
Comments
8 min read
Copying without attention: Fourier readout of a fixed-size wave memory

Copying without attention: Fourier readout of a fixed-size wave memory

Comments
22 min read
Why Do AI Models Need High-Dimensional Embeddings?

Why Do AI Models Need High-Dimensional Embeddings?

3
Comments
2 min read
Beyond Static Layers: The Architecture of Mixture-of-Depths (MoD)

Beyond Static Layers: The Architecture of Mixture-of-Depths (MoD)

Comments
2 min read
SinkState: Scaling Hybrid LLMs with On-the-Fly SVD and Adaptive Low-Rank States

SinkState: Scaling Hybrid LLMs with On-the-Fly SVD and Adaptive Low-Rank States

Comments
5 min read
How Open-Source LLMs Differ: Comparing 130+ Model Architectures

How Open-Source LLMs Differ: Comparing 130+ Model Architectures

5
Comments 1
7 min read
Building Road Infrastructure Digital Twins with Computer Vision & Deep Learning

Building Road Infrastructure Digital Twins with Computer Vision & Deep Learning

Comments
3 min read
My depth model was obsessed with the sky. Here's how I made it care about cars.

My depth model was obsessed with the sky. Here's how I made it care about cars.

1
Comments
5 min read
FlashAttention: Why Tiling Attention Makes Transformers Fast Without Changing the Result

FlashAttention: Why Tiling Attention Makes Transformers Fast Without Changing the Result

Comments
11 min read
Reverse-Engineering the Black Box: The Science of Mechanistic Interpretability

Reverse-Engineering the Black Box: The Science of Mechanistic Interpretability

Comments
3 min read
Praxis-1: How Runway Turned a Video Foundation Model Into a Robot Brain

Praxis-1: How Runway Turned a Video Foundation Model Into a Robot Brain

Comments
5 min read
From Lab to Code #4: Exploring Neural Network Efficiency with Python and PyTorch

From Lab to Code #4: Exploring Neural Network Efficiency with Python and PyTorch

Comments
12 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.